DenseNet3D and DenseNet3D-FCN models for Keras.

Adapted DenseNet and DensetNet-FCN to work with 3D input for volume classification and segmentation.

DenseNet is a network architecture where each layer is directly connected to every other layer in a feed-forward fashion (within each dense block). For each layer, the feature maps of all preceding layers are treated as separate inputs whereas its own feature maps are passed on as inputs to all subsequent layers. This connectivity pattern yields state-of-the-art accuracies on CIFAR10/100 (with or without data augmentation) and SVHN. On the large scale ILSVRC 2012 (ImageNet) dataset, DenseNet achieves a similar accuracy as ResNet, but using less than half the amount of parameters and roughly half the number of FLOPs.

DenseNets can be extended to image segmentation tasks as described in the paper "The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation". Here, the dense blocks are arranged and concatenated with long skip connections for state of the art performance on the CamVid dataset.